Renhao Wang

I am a PhD student at UC Berkeley, advised by Prof. Alexei A. Efros, working on problems at the intersection of computer vision and robotics. I'm particularly interested in how we can use self-supervised learning for building embodied systems that continuously learn and evolve in the real world.

Previously, I also acted as Chief Scientist at PeerWell, working on machine learning for health (acquired by Bardavon Health Innovations.)


Publications


Prioritized Generative Replay

  • Renhao Wang, Kevin Frans, Pieter Abbeel, Sergey Levine, Alexei A. Efros
  • ICLR 2025 [Oral, Top 1.8%]
  • paper | project page | code

Test-Time Training on Video Streams

  • Renhao Wang*, Yu Sun*, Yossi Gandelsman, Xinlei Chen, Alexei A. Efros, Xiaolong Wang
  • JMLR 2025.
  • paper | project page | code

Programmatically Grounded, Compositionally Generalization Robotic Manipulation

  • Renhao Wang, Jiayuan Mao, Joy Hsu, Hang Zhao, Yang Gao, Jiajun Wu
  • ICLR 2023 [Oral, Top 25%]
  • paper | project page

Robust and Controllable Object-Centric Learning through Energy-based Models

  • Ruixiang Zhang, Tong Che, Boris Ivanovic, Renhao Wang, Marco Pavone, Yoshua Bengio, Liam Paull
  • ICLR 2023.
  • paper

CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in Segmentation

Semantic-Aware Fine-Grained Correspondence

  • Yingdong Hu, Renhao Wang, Kaifeng Zhang, Yang Gao
  • ECCV 2022 [Oral, Top 2.3%]
  • paper | project page | code

Equivariant Maps for Hierarchical Structures

  • Renhao Wang, Marjan Albooyeh, Siamak Ravanbakhsh
  • NeurIPS 2020 [Oral, Top 1.1%]
  • paper | project page | code

Template graciously lended by Yossi Gandelsman.